system

Abstract

We provide the system. [Solution] A means of collecting past behavioral data of participants and storing it in a database, A method for analyzing participants' past behavioral data using a generative model and generating an optimal event schedule for each participant, A means of sending and displaying the generated event schedule on the participants' devices, A means of accepting schedule adjustments from participants and managing updated schedules, A means for participants to share the generated schedule with other participants, A system that includes this.

Description

Technical Field

[0001] The technology of the present disclosure relates to a system.

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In large-scale events, participants may struggle to make the most suitable choices according to their interests while many activities are being carried out simultaneously. Also, creating a schedule that reflects individual interests requires time and effort, and the opportunities to promote communication among participants are limited. These problems are factors that impair the event participation experience and are important improvement points for event organizers.

Means for Solving the Problems

[0005] This invention provides a system that collects past behavioral data of participants and generates individually optimized event schedules using an analytical means that utilizes a generative model. This system improves usability by directly transmitting and displaying the generated schedule on the participant's terminal. In addition, participants can adjust and share their own schedules, promoting interaction with other participants who share similar interests. Furthermore, the system aims to improve accuracy by incorporating feedback data collected during participation into the generation of future schedules.

[0006] "Participant behavioral data" refers to data that records participants' behavioral history at events, selected activities, and trends in interests and preferences.

[0007] "Means of storing data in a database" refers to a system for efficiently saving collected data and making it easily accessible later.

[0008] A "generative model" is an algorithm or learning model that extracts patterns and relationships from large amounts of data to generate new schedules or predictions.

[0009] "Means of sending and displaying on a terminal" refers to technologies for sending information generated from a server to a user's device and visually presenting it on the screen.

[0010] "A means of accepting schedule adjustments and managing updated schedules" refers to a function that accepts changes made to the schedule by participants and appropriately organizes and manages them.

[0011] "Means for participants to share generated schedules with other participants" refers to technology that allows multiple participants to exchange their schedule information with each other.

[0012] "Feedback data" refers to information such as comments and suggestions for improvement provided by participants after the event, and is used as reference for future events. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiment for Carrying Out the Invention

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), etc.

[0017] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0019] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] This invention is a system for providing event participants with an optimal event schedule tailored to their individual interests. This system consists of three components: a server, a terminal, and a user.

[0035] First, the server collects past behavioral data from participants. This behavioral data is based on participants' past participation activities and interests in events. This data is stored in a database on the server and can be retrieved as needed.

[0036] Next, the server uses the accumulated data to perform analysis through a generative model. The generative model analyzes participants' past behavioral patterns and generates an optimal schedule based on each participant's interests. The generated schedule is prioritized and designed so that users can participate in the activities that interest them most first.

[0037] The generated schedule is sent from the server to each participant's terminal. The terminal provides an interface to visually present the received schedule to the user. The user can review the provided schedule and make adjustments according to their interests.

[0038] For example, if a user prioritizes a particular activity, they can adjust the time for that activity on the schedule displayed on their device. Once the schedule is adjusted, the device resends it to the server to maintain its current state.

[0039] Furthermore, users can share the generated schedule with other participants. This provides an easy way for participants with similar interests to interact. After participating, users enter feedback about their event experience on their device and send it to the server. This feedback helps improve the accuracy of schedule generation for future events.

[0040] In this way, this system provides schedules optimized to each user's preferences, promotes interaction among participants, and enhances the event participation experience.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The server collects past behavioral data from event participants. This includes activities they participated in, their ratings, and topics of interest, and stores this data in a database.

[0044] Step 2:

[0045] The server uses a generative model to analyze the interests of each participant based on the collected data. This generates an event schedule optimized for each participant.

[0046] Step 3:

[0047] The server sends the generated schedule to each participant's device. The device then displays the received schedule in its user interface, providing it visually.

[0048] Step 4:

[0049] Users can check their schedules on their devices and manually adjust them as needed. For example, they can delete lower-priority events or adjust their times.

[0050] Step 5:

[0051] The terminal sends the user's schedule adjustments to the server in real time. The server manages the latest schedule and synchronizes schedules with other participants as needed.

[0052] Step 6:

[0053] Users can share their schedules with other participants. In this process, the device generates a sharing link and exchanges schedule information.

[0054] Step 7:

[0055] After the event ends, users enter feedback from their devices and send it to the server. The server stores this feedback data in a database and uses it to generate the schedule for the next event.

[0056] (Example 1)

[0057] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0058] In today's diverse world of events, it is crucial to provide participants with optimal event schedules tailored to their individual interests and past behavioral patterns. However, conventional schedule provision systems struggle to adequately consider the individuality of each participant. Specifically, for events with many participants attending simultaneously, there is a need for an efficient and effective system that automatically adjusts schedules to reflect each individual's interests and presents the results quickly.

[0059] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0060] In this invention, the server includes means for aggregating participants' past activity data and storing it in an information storage device, means for analyzing participants' past activity data using a generation algorithm and generating an optimal event schedule for each participant, and means for transmitting and displaying the generated event schedule to the participants' communication devices. This makes it possible to create flexible schedules that reflect the interests of individual participants.

[0061] "Participants" refers to individuals or people who participate in activities or events within a given event.

[0062] "Activity data" refers to information about participants' past event participation history and behavioral patterns based on their interests.

[0063] An "information storage device" refers to a device that has the function of systematically storing data and allowing it to be referenced as needed.

[0064] A "generative algorithm" refers to a computational method used to analyze participant activity data and derive the optimal event schedule.

[0065] "Event schedule" refers to a schedule that shows the times and order of events and activities that participants can take part in.

[0066] "Communication device" refers to an electronic device used to send and receive information to and from participants.

[0067] The system in this invention is an advanced technology that generates an optimal event schedule based on participants' interests. To implement the invention, the system mainly consists of three entities: a "server," a "terminal," and a "user." Each entity plays a specific role, and the system functions effectively by coordinating with each other as a whole.

[0068] First, the server collects participants' past activity data and stores it in an information storage device. This information storage device is implemented in a format such as an SQL database, efficiently managing participants' past event participation history and interest data. The server also uses a generation algorithm to analyze participants' activity data and generate an optimal event schedule for each participant. A widely used machine learning model can be applied as the generation algorithm, enabling the generation of schedules that take into account the different interests and preferences of participants.

[0069] Next, the server transmits the generated event schedule to the participants' communication devices, i.e., terminals. The terminals provide an interface for visually presenting this schedule to the users. Specifically, the terminals receive the data and display it visually through the user interface in a way that is intuitively easy for participants to understand.

[0070] Users can use the terminal interface to review the presented event schedule and make adjustments according to their interests and convenience. For example, if they want to prioritize a particular activity, they can change the time of that activity on the terminal. The adjusted event schedule is then sent back to the server and recorded as the latest state in the server's information storage device. This ensures that participants have the optimal experience according to the time.

[0071] As a concrete example of such a system, if a participant is interested in art, the server considers that participant's past participation history in art-related events and prioritizes scheduling museum visits, painting workshops, and similar activities. This allows participants to attend events that best match their interests.

[0072] As an example of a prompt in a generative AI model, the instructions the system receives might be the following text:

[0073] "Based on participants' past activity data, generate an optimal event schedule. Prioritize activities that will pique their interest and propose a visually clear and easy-to-understand format for displaying the schedule on their devices."

[0074] This prompt allows the system to leverage its technical advantages to design an event experience that aligns with the individual needs of each participant.

[0075] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0076] Step 1:

[0077] The server collects data on participants' past activities.

[0078] The system acquires data such as event participation history and areas of interest as input, and stores this data in an information storage device on the server. Specifically, the server retrieves data from various sources, organizes it in an SQL database, and stores it. This creates a comprehensive profile of the participant's preferences and interests.

[0079] Step 2:

[0080] The server uses a generated AI model to analyze the collected activity data.

[0081] The server receives accumulated data as input and prompts the generating AI model to perform analysis. Specifically, the AI ​​model analyzes the participants' past behavioral patterns and generates an optimal event schedule for each participant. This process utilizes machine learning algorithms, and the output is a prioritized event schedule.

[0082] Step 3:

[0083] The server sends the generated event schedule to the terminal.

[0084] The event schedule generated by the AI ​​model is used as input, and the server converts it into JSON format and transmits it to the terminal. Specifically, data is transferred from the server to the terminal using the HTTP protocol, and the terminal receives it. This prepares the event information that is most suitable for the participant.

[0085] Step 4:

[0086] The terminal visually displays the received event schedule to the user.

[0087] The event schedule received from the server is used as input, and the terminal provides an interface to visually display it. Specifically, a graphical user interface is used to display the schedule and activity details on the screen. This makes it easier for the user to intuitively understand the event schedule.

[0088] Step 5:

[0089] The user reviews the presented schedule and makes adjustments as needed.

[0090] The input is an event schedule displayed on the device, and the user adjusts the schedule through drag-and-drop and other methods. Specifically, it is possible to select activities that are prioritized and change their time and order. This operation enables the customization of the schedule to suit the user's individual interests.

[0091] Step 6:

[0092] The terminal resends the adjusted schedule to the server.

[0093] The event schedule, modified by the user, is used as input, and the terminal sends it back to the server in JSON format. In the actual processing, the server records this data again in the information storage device, keeping it up-to-date. This ensures that participants' schedules are always managed based on the latest information.

[0094] (Application Example 1)

[0095] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0096] Existing content distribution services face the challenge of efficiently providing content tailored to user interests. In particular, they lack sufficient individualized support that leverages the characteristics of visual display devices, limiting the user experience. Therefore, there is a need for more personalized content presentation and scheduling based on user interests and behavioral patterns.

[0097] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0098] In this invention, the server includes means for collecting past behavioral data of participants and storing it in an information storage device; means for analyzing past behavioral data of participants using a generation model and generating an optimal timetable for each participant; means for transmitting and displaying the generated timetable on the participant's information terminal; means for presenting a content list to participants using a visual display device; means for synchronizing selected content from the content list with the information storage device and coordinating information with other devices; and means for collecting participants' feedback or evaluation information and reflecting it in the generation of the next timetable. This enables individually optimized display of content according to user interests, as well as real-time synchronization and adjustment of information.

[0099] A "participant" is a user of the service within the system and the entity that provides information about their individual actions.

[0100] "Behavioral data" refers to information that records the choices and activities that participants have made in the past, and it is the data that forms the basis of the analysis.

[0101] An "information storage device" is a storage medium within a system that stores accumulated behavioral data and generated timetables.

[0102] A "generative model" is a mathematical or algorithmic computational method used to analyze past behavioral data.

[0103] A "timetable" is a plan or schedule created to guide participants' activities based on the analysis results.

[0104] An "information terminal" is an electronic device used by participants to access the system's functions.

[0105] A "visual display device" is a display device used to provide information to participants visually, and includes glasses-type devices.

[0106] A "content list" is a list of information or media items selected based on the participants' interests.

[0107] "Information sharing" refers to the act of synchronizing or sharing data between multiple devices.

[0108] "Feedback or evaluation information" refers to the subjective evaluations that participants give to content or services, and this data is used to optimize future offerings.

[0109] The system realizing this invention utilizes various devices and software to deliver and schedule optimal content based on participants' interests. The main components are a server, an information terminal, and a visual display device.

[0110] The server collects and stores participants' past behavioral data using an information storage device. A cloud database such as Firebase is used for this purpose. Next, a generative AI model such as TENSORFLOW® is used to analyze the collected behavioral data and generate a personalized schedule based on the participants' interests. The generated schedule is then transmitted to the participants' information terminals via the cloud service.

[0111] Participants' information terminals will use Flutter® or similar technologies to build a user interface and display the generated timetable. Visual display devices, such as eyeglasses (Google® Glass®, etc.), will present users with a content list in real time, and users will select content of interest from that list. The selected content will be synchronized via Firebase, maintaining information sharing with other devices.

[0112] Furthermore, users input their impressions and evaluations of the provided content and send them from their devices to the server. This feedback information plays a crucial role in the optimization process for generating future schedules and content lists.

[0113] As a concrete example, consider the presentation of content at a music festival. Based on data from artists the user has watched in the past, they are recommended appropriate live performances from artists scheduled to participate in the next festival. In this case, an example of a prompt would be, "Based on the user's past viewing history, please suggest new live videos this week that might be of particular interest to them."

[0114] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0115] Step 1:

[0116] The server collects participants' past behavioral data from a cloud database. The input is behavioral data stored in cloud storage, and the output is a dataset for analysis. This dataset integrates information including participants' past choices and interests.

[0117] Step 2:

[0118] The server analyzes the collected dataset using a generative AI model. The input is the dataset from Step 1, and the output is a timetable optimized for each participant. The AI ​​model analyzes patterns in the data and identifies the content and activities that best match the participants' interests.

[0119] Step 3:

[0120] The server sends the generated timetable to the participants' information terminals via the cloud. The input here is the timetable generated in step 2, and the output is a visual display of the timetable on the terminal. The information terminal displays this timetable in its user interface, making it easy for participants to check.

[0121] Step 4:

[0122] The user reviews a list of content presented through a visual display device and selects content of interest. The input is the content list displayed on the terminal, and the output is information about the selected content. This selection information is transmitted from the visual display device to the terminal and synchronized for the next step.

[0123] Step 5:

[0124] The terminal synchronizes the content information selected by the user to a cloud database. The input is the content information selected in step 4, and the output is the synchronization status to the information storage device. The cloud database receives this and uses it as data to interact with other devices.

[0125] Step 6:

[0126] Users input their thoughts and evaluations of the content from their devices and send them to the server. The input consists of user evaluation comments and feedback data, while the output is a feedback record used in the next optimization process. The server stores this feedback information and incorporates it into the next timetable generation.

[0127] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0128] This invention provides a system that offers an event schedule based on participants' interests and combines it with an emotion engine that recognizes users' emotions. The system aims to provide participants with a more highly personalized event experience.

[0129] This system primarily consists of four components: a server, a terminal, a user, and an emotion engine. First, the server collects past behavioral data from participants and stores it in a database. This data includes events the participant has previously attended, topics they have shown interest in, and their ratings. Based on the collected data, the server uses a generative model to analyze the data and generate an optimized event schedule for each participant.

[0130] The generated schedule is sent from the server to each participant's device and displayed on their device. Users can review this schedule and make manual adjustments as needed. The adjusted schedule is sent to the server in real time and kept up-to-date on the server.

[0131] A distinctive component of this invention is an emotion engine. The emotion engine recognizes emotions in real time from the user's facial expressions, tone of voice, and other factors. This information is used by the server to optimize the schedule. For example, if a user shows positive emotions towards a particular activity, the server will set a higher priority for that activity. If a user shows negative emotions, the server can suggest alternative activities and automatically restructure the schedule.

[0132] For example, if the emotion engine detects many positive emotions from a user on the first day of an exhibition, the server will present a schedule for the second day that reflects an increase in activities similar to those of that user. Conversely, for sessions with negative ratings, similar activities can be removed to improve the overall experience. In this way, the system can incorporate real-time emotion information from users and provide an event experience optimized for participants.

[0133] The following describes the processing flow.

[0134] Step 1:

[0135] The server collects past behavioral data from event participants and stores it in a database. This includes detailed information such as the activities they participated in and the topics they showed interest in.

[0136] Step 2:

[0137] The server uses a generative model to analyze the collected behavioral data. This generates an optimized event schedule for each participant, creating a schedule tailored to individual interests.

[0138] Step 3:

[0139] The server sends the generated schedule to the participants' devices. The devices then visually display this schedule to the users and prompt them for confirmation.

[0140] Step 4:

[0141] Users check the schedule displayed on their device and make manual adjustments as needed. These adjustments include changing the priority of activities they want to participate in and rearranging the times.

[0142] Step 5:

[0143] The terminal sends the user's adjustments to the server in real time, and the latest information is managed on the server.

[0144] Step 6:

[0145] The emotion engine recognizes the user's facial expressions and voice tone in real time and generates emotion data. This emotion data is categorized into positive, negative, neutral, and other categories.

[0146] Step 7:

[0147] The server re-evaluates the schedule based on the emotion data received from the emotion engine. If the emotion is positive, it prioritizes the relevant activity; if the emotion is negative, it suggests an alternative activity.

[0148] Step 8:

[0149] The device notifies the user of the re-evaluated schedule and presents a new schedule that reflects the suggestions.

[0150] Step 9:

[0151] After the event ends, users enter feedback from their devices and send it to the server. This feedback data is used to generate future event schedules and is reflected in the analysis results.

[0152] (Example 2)

[0153] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0154] Current event scheduling systems have the challenge of making it difficult to provide an experience optimized for each individual participant. Specifically, they cannot reflect participants' individual interests and emotions in real time, and are limited to providing an experience based on a fixed schedule. As a result, it becomes difficult to improve participant satisfaction.

[0155] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0156] In this invention, the server includes means for collecting information on participants' past behavior and storing it in an information storage medium; means for analyzing the participants' past behavior information using a generative model and generating an optimal activity schedule for each participant; and means for analyzing the characteristics of participants' facial expressions and voices and acquiring emotional information. This makes it possible to provide an optimized activity schedule in real time according to the participants' interests and emotions.

[0157] "Participants" refers to individual users involved in an event or activity.

[0158] "Past behavioral information" refers to data about events participants have previously attended, their interests, and their evaluations.

[0159] An "information storage medium" refers to a storage device used to accumulate and manage data.

[0160] A "generative model" refers to an algorithm or method used to analyze data and generate specific deliverables.

[0161] "Activity schedule" refers to a schedule outlining the events and activities that participants will be taking part in in the future.

[0162] "Information terminal" refers to an electronic device used by participants to receive, view, or manipulate information.

[0163] "Facial and vocal characteristics" refers to visual or auditory information obtained from the participants' facial expressions and speech.

[0164] "Emotional information" refers to data that indicates the emotional state of participants.

[0165] Prioritization refers to the act of assigning relative importance to a series of items or tasks.

[0166] "Evaluation information" refers to data that shows the opinions and impressions that participants have about their experiences and activities.

[0167] To implement this invention, a system consisting mainly of a server, terminal, user, and emotion engine is constructed.

[0168] The server acts as the central hub, collecting and processing information about the past behavior of participating users. This includes events the user has previously attended, topics they have shown interest in, and their ratings. A common database management system can be used to store this data. Furthermore, the server uses a generative AI model to analyze this data and create an activity schedule optimized for the user. This process can utilize programming languages ​​such as Python or machine learning libraries such as TensorFlow.

[0169] The terminal functions as a device for users to check their activity schedule and edit it as needed. Schedules sent from the server are displayed on the terminal. Users can adjust their schedules on this terminal, and these adjustments are immediately sent to the server. The HTTP protocol could be used for this.

[0170] Furthermore, this invention includes an emotion engine. The emotion engine acquires emotional information from the user's facial expressions and voice. This information is collected using a camera and microphone and analyzed using OpenCV or other speech recognition technologies. Based on this emotional information, the server can further personalize the user's schedule.

[0171] For example, if a user expresses positive emotions through the emotion engine on the first day of an exhibition, the server will generate a schedule for the second day that includes similar activities. Conversely, for sessions that receive negative ratings, similar content can be removed, and the schedule can be reorganized to provide a better experience.

[0172] An example of a prompt message is, "Generate an optimal schedule based on the user's preferred activities and readjust it to reflect sentiment data." This allows the system to provide a more personalized activity experience optimized for the participant.

[0173] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0174] Step 1:

[0175] The server collects information about the user's past behavior and stores it in a data storage medium. Specifically, it obtains data such as events the user has previously participated in, topics they are interested in, and ratings through APIs and log files. This input data is stored in a structured format using a database management system.

[0176] Step 2:

[0177] The server performs data analysis using a generative AI model based on collected past behavioral information. This analysis extracts user interests and tendencies and generates an optimal activity plan. Here, behavioral information stored in the database is taken as input, and a predicted activity plan is obtained as output. Statistical calculations are performed using a machine learning framework.

[0178] Step 3:

[0179] The server sends the generated activity schedule to the user's terminal. This process uses the HTTP protocol to send the schedule information to the terminal in JSON format. The terminal receives this data as input and displays the schedule in the user interface.

[0180] Step 4:

[0181] Users review their activity schedule displayed on their device and make adjustments as needed. Specifically, they can change, add, or delete appointments using drag-and-drop functionality or selection buttons. This adjusted schedule is then resent from the device to the server, where it is updated to the latest state.

[0182] Step 5:

[0183] The emotion engine analyzes the user's facial expressions and voice tone in real time to acquire emotional information. It inputs data using a camera and microphone, and converts it into emotional information using OpenCV and speech recognition technology. This information generates output indicating the user's current emotional state.

[0184] Step 6:

[0185] The server uses the acquired sentiment information to automatically readjust the activity schedule. It receives sentiment information as input, prioritizes activities that elicit positive emotions from the user, and suggests alternatives for activities that receive negative ratings. This readjusted schedule is then generated and sent back to the device.

[0186] (Application Example 2)

[0187] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0188] Modern commercial facilities and event venues are required to provide visitors with personalized experiences. Traditional methods struggle to deliver the optimal experience tailored to participants' interests and lack the ability to dynamically adjust in real time to reflect emotions and interests. In particular, there is a need to quickly reflect collected emotional information and individually optimize the visitor experience.

[0189] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0190] In this invention, the server includes means for collecting and storing past behavioral data of participants in a database, means for analyzing past behavioral data of participants using a generative model and generating an optimal event plan for each participant, and means for acquiring participants' emotional information in real time and dynamically optimizing the event plan using that information. This makes it possible to provide a personalized experience based on participants' past behavior and real-time emotions, thereby improving visitor satisfaction.

[0191] "Participants" are individuals who visit a specific event or commercial facility.

[0192] "Behavioral data" refers to a collection of information about the actions and choices that participants have made in the past.

[0193] A "database" is a system that stores data and enables efficient management and retrieval.

[0194] A "generative model" is an algorithm that analyzes participants' behavioral data and generates results tailored to a specific purpose.

[0195] An "event plan" is a proposed schedule that optimizes the events and activities that participants will experience.

[0196] "Information processing equipment" refers to electronic devices such as mobile terminals and computers used by participants.

[0197] "Emotional information" refers to data about the emotional state obtained from participants' facial expressions and voice.

[0198] "Dynamic optimization" is a process of immediately adjusting plans and proposals based on real-time information.

[0199] "Evaluation information" refers to data that includes opinions and impressions of participants' experiences.

[0200] The system that realizes this invention consists of a server, terminals, users, and an emotion engine that complements them. The server accesses a database to collect and store past behavioral data of participants and analyzes it using a generative model to generate an optimized event plan for each participant. This makes it possible to personalize events based on participants' past interests and behaviors.

[0201] The generated event plan is transmitted via the internet to participants' information processing devices (e.g., smartphones, tablets). The devices display the received information, allowing participants to review and adjust the plan based on this information. This adjustment information is then sent back to the server and updated in real time.

[0202] The emotion engine collects user facial expressions via camera and audio via microphone, extracting emotional information in real time. Specifically, it performs image analysis using OpenCV and DeepFace, converts audio to text using the Google Cloud Speech-to-Text API, and then evaluates emotions using natural language processing techniques. This allows the system to dynamically adjust plans according to the user's emotions, providing a better experience.

[0203] For example, when a user is searching for products in a store, if their facial expression is positively recognized by their smartphone camera, the server can prioritize suggesting products from a specific brand. Conversely, if there is a negative reaction, the server will refrain from suggesting related products.

[0204] An example of a prompt to input into the generating AI model is: "Identify in real time what products the user is interested in in a physical store, and consider how to present the most suitable offers and information for that day." This prompt is used to generate a scenario that personalizes product suggestions for the user.

[0205] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0206] Step 1:

[0207] The server collects past behavioral data from participants from a database. Inputs include past behavioral records, topics of interest, and evaluation data. Based on this data, the server organizes and integrates the participants' past history and prepares it for analysis.

[0208] Step 2:

[0209] The server uses the collected behavioral data to launch a generative model and perform analysis. The input is behavioral data, and the generative AI model is used to analyze behavioral patterns and their correlations. As output, an event plan optimized for each participant is generated.

[0210] Step 3:

[0211] The server sends the generated event plan to the participants' terminals via the internet. The terminals receive this event plan internally and display it visually on their screens. The input here is the event plan data, and the output is what is displayed on the terminals.

[0212] Step 4:

[0213] Users view the event schedule displayed on their terminal and make adjustments as needed. Users input requests such as desired destinations and time slots. The terminal receives this information and resends it to the server, updating the schedule.

[0214] Step 5:

[0215] The emotion engine captures the user's facial expressions with a camera and records their voice with a microphone. The input consists of the user's real-time facial expressions and voice. OpenCV and the Google Cloud Speech-to-Text API are used to extract this data as emotional information. The output is a positive or negative emotional evaluation.

[0216] Step 6:

[0217] The server dynamically optimizes event plans using emotion information received in real time. Inputs are emotion information and existing event plans, and the system uses a generative AI model to adjust the plans. The output is an updated event plan based on the emotions.

[0218] Step 7:

[0219] The terminal receives the updated event plan again from the server and presents it to the user. The final output is a display of the optimized event plan, with an example prompt message being, "Identify in real time what products the user is interested in in-store and consider how to present the most suitable offers and information for that day."

[0220] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0221] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0222] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0223] [Second Embodiment]

[0224] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0225] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0226] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0227] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0228] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0229] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0230] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0231] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0232] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0233] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0234] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0235] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0236] This invention is a system for providing event participants with an optimal event schedule tailored to their individual interests. This system consists of three components: a server, a terminal, and a user.

[0237] First, the server collects past behavioral data from participants. This behavioral data is based on participants' past participation activities and interests in events. This data is stored in a database on the server and can be retrieved as needed.

[0238] Next, the server uses the accumulated data to perform analysis through a generative model. The generative model analyzes participants' past behavioral patterns and generates an optimal schedule based on each participant's interests. The generated schedule is prioritized and designed so that users can participate in the activities that interest them most first.

[0239] The generated schedule is sent from the server to each participant's terminal. The terminal provides an interface to visually present the received schedule to the user. The user can review the provided schedule and make adjustments according to their interests.

[0240] For example, if a user prioritizes a particular activity, they can adjust the time for that activity on the schedule displayed on their device. Once the schedule is adjusted, the device resends it to the server to maintain its current state.

[0241] Furthermore, users can share the generated schedule with other participants. This provides an easy way for participants with similar interests to interact. After participating, users enter feedback about their event experience on their device and send it to the server. This feedback helps improve the accuracy of schedule generation for future events.

[0242] In this way, this system provides schedules optimized to each user's preferences, promotes interaction among participants, and enhances the event participation experience.

[0243] The following describes the processing flow.

[0244] Step 1:

[0245] The server collects past behavioral data from event participants. This includes activities they participated in, their ratings, and topics of interest, and stores this data in a database.

[0246] Step 2:

[0247] The server uses a generative model to analyze the interests of each participant based on the collected data. This generates an event schedule optimized for each participant.

[0248] Step 3:

[0249] The server sends the generated schedule to each participant's device. The device then displays the received schedule in its user interface, providing it visually.

[0250] Step 4:

[0251] Users can check their schedules on their devices and manually adjust them as needed. For example, they can delete lower-priority events or adjust their times.

[0252] Step 5:

[0253] The terminal sends the user's schedule adjustments to the server in real time. The server manages the latest schedule and synchronizes schedules with other participants as needed.

[0254] Step 6:

[0255] Users can share their schedules with other participants. In this process, the device generates a sharing link and exchanges schedule information.

[0256] Step 7:

[0257] After the event ends, users enter feedback from their devices and send it to the server. The server stores this feedback data in a database and uses it to generate the schedule for the next event.

[0258] (Example 1)

[0259] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0260] In today's diverse world of events, it is crucial to provide participants with optimal event schedules tailored to their individual interests and past behavioral patterns. However, conventional schedule provision systems struggle to adequately consider the individuality of each participant. Specifically, for events with many participants attending simultaneously, there is a need for an efficient and effective system that automatically adjusts schedules to reflect each individual's interests and presents the results quickly.

[0261] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0262] In this invention, the server includes means for aggregating participants' past activity data and storing it in an information storage device, means for analyzing participants' past activity data using a generation algorithm and generating an optimal event schedule for each participant, and means for transmitting and displaying the generated event schedule to the participants' communication devices. This makes it possible to create flexible schedules that reflect the interests of individual participants.

[0263] "Participants" refers to individuals or people who participate in activities or events within a given event.

[0264] "Activity data" refers to information about participants' past event participation history and behavioral patterns based on their interests.

[0265] An "information storage device" refers to a device that has the function of systematically storing data and allowing it to be referenced as needed.

[0266] A "generative algorithm" refers to a computational method used to analyze participant activity data and derive the optimal event schedule.

[0267] "Event schedule" refers to a schedule that shows the times and order of events and activities that participants can take part in.

[0268] "Communication device" refers to an electronic device used to send and receive information to and from participants.

[0269] The system in this invention is an advanced technology that generates an optimal event schedule based on participants' interests. To implement the invention, the system mainly consists of three entities: a "server," a "terminal," and a "user." Each entity plays a specific role, and the system functions effectively by coordinating with each other as a whole.

[0270] First, the server collects participants' past activity data and stores it in an information storage device. This information storage device is implemented in a format such as an SQL database, efficiently managing participants' past event participation history and interest data. The server also uses a generation algorithm to analyze participants' activity data and generate an optimal event schedule for each participant. A widely used machine learning model can be applied as the generation algorithm, enabling the generation of schedules that take into account the different interests and preferences of participants.

[0271] Next, the server transmits the generated event schedule to the participants' communication devices, i.e., terminals. The terminals provide an interface for visually presenting this schedule to the users. Specifically, the terminals receive the data and display it visually through the user interface in a way that is intuitively easy for participants to understand.

[0272] Users can use the terminal interface to review the presented event schedule and make adjustments according to their interests and convenience. For example, if they want to prioritize a particular activity, they can change the time of that activity on the terminal. The adjusted event schedule is then sent back to the server and recorded as the latest state in the server's information storage device. This ensures that participants have the optimal experience according to the time.

[0273] As a concrete example of such a system, if a participant is interested in art, the server considers that participant's past participation history in art-related events and prioritizes scheduling museum visits, painting workshops, and similar activities. This allows participants to attend events that best match their interests.

[0274] As an example of a prompt in a generative AI model, the instructions the system receives might be the following text:

[0275] "Based on participants' past activity data, generate an optimal event schedule. Prioritize activities that will pique their interest and propose a visually clear and easy-to-understand format for displaying the schedule on their devices."

[0276] This prompt allows the system to leverage its technical advantages to design an event experience that aligns with the individual needs of each participant.

[0277] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0278] Step 1:

[0279] The server collects data on participants' past activities.

[0280] The system acquires data such as event participation history and areas of interest as input, and stores this data in an information storage device on the server. Specifically, the server retrieves data from various sources, organizes it in an SQL database, and stores it. This creates a comprehensive profile of the participant's preferences and interests.

[0281] Step 2:

[0282] The server uses a generated AI model to analyze the collected activity data.

[0283] As input, the accumulated data is provided, and the server presents a prompt sentence to the generative AI model and requests an analysis. Specifically, the AI model analyzes the past behavior patterns of the participants and generates an optimal event schedule for the participants. In this process, machine learning algorithms are used, and the output is an event schedule with priorities.

[0284] Step 3:

[0285] The server sends the generated event schedule to the terminal.

[0286] As input, the event schedule generated by the AI model is used, and the server converts it into JSON format and transmits it to the terminal. As a specific operation, data transfer using the HTTP protocol from the server to the terminal is performed, and the terminal receives it. Thereby, information on the events most suitable for the participants is prepared.

[0287] Step 4:

[0288] The terminal visually presents the received event schedule to the user.

[0289] As input, the event schedule received from the server is used, and the terminal provides an interface for visually displaying it. As a specific operation, a graphical user interface is utilized, and the schedule and activity details are displayed on the screen. Thereby, it becomes easier for the user to intuitively understand the event schedule.

[0290] Step 5:

[0291] The user checks the presented schedule and makes adjustments if necessary.

[0292] As input, there is an event schedule displayed on the terminal, and the user adjusts the schedule through operations such as drag & drop. In a specific operation, it is possible to select the activities to be prioritized and change the time and order. By this operation, customization of the schedule according to the individual interests of the user is realized.

[0293] Step 6:

[0294] The terminal resends the adjusted schedule to the server.

[0295] The event schedule, modified by the user, is used as input, and the terminal sends it back to the server in JSON format. In the actual processing, the server records this data again in the information storage device, keeping it up-to-date. This ensures that participants' schedules are always managed based on the latest information.

[0296] (Application Example 1)

[0297] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0298] Existing content distribution services face the challenge of efficiently providing content tailored to user interests. In particular, they lack sufficient individualized support that leverages the characteristics of visual display devices, limiting the user experience. Therefore, there is a need for more personalized content presentation and scheduling based on user interests and behavioral patterns.

[0299] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0300] In this invention, the server includes means for collecting the past behavior data of participants and storing it in an information storage device, means for analyzing the past behavior data of participants using a generation model and generating an optimal schedule for each participant, means for transmitting and displaying the generated schedule on the information terminals of participants, means for presenting a content list to participants by a visual display device, means for synchronizing the content selected from the content list with the information storage device and performing information sharing with other devices, and means for collecting the impressions or evaluation information of participants and reflecting it in the next schedule generation. Thereby, it becomes possible to individually optimize the display of content according to the interests of users, and to perform real-time synchronization and adjustment of information.

[0301] A "participant" is a user of the service in the system and a subject that provides individual behavior information.

[0302] "Behavior data" is information that records the selections and activities that participants have carried out in the past, and is the data that serves as the basis for analysis.

[0303] An "information storage device" is a storage medium within the system that stores the accumulated behavior data and the generated schedule.

[0304] A "generation model" is a mathematical or algorithmic calculation method used to analyze past behavior data.

[0305] A "schedule" is a plan or schedule created to guide the activities of participants based on the analysis results.

[0306] An "information terminal" is an electronic device used by participants to utilize the functions of the system.

[0307] A "visual display device" is a display device for visually providing information to participants, including glasses-type devices.

[0308] A "content list" is a list of items of information or media selected based on the interests of participants.

[0309] "Information sharing" refers to the act of synchronizing or sharing data between multiple devices.

[0310] "Feedback or evaluation information" refers to the subjective evaluations that participants give to content or services, and this data is used to optimize future offerings.

[0311] The system realizing this invention utilizes various devices and software to deliver and schedule optimal content based on participants' interests. The main components are a server, an information terminal, and a visual display device.

[0312] The server collects and stores participants' past behavioral data using an information storage device. A cloud database such as Firebase is used for this purpose. Next, a generative AI model such as TensorFlow is used to analyze the collected behavioral data and generate a personalized schedule based on the participants' interests. The generated schedule is then sent to the participants' information terminals via the cloud service.

[0313] Participants' information terminals will use Flutter or similar tools to build a user interface and display the generated timetable. Visual display devices, such as glasses (Google Glass, for example), will present users with a list of content in real time, and users will select content of interest from that list. The selected content will be synchronized via Firebase, maintaining information sharing with other devices.

[0314] Furthermore, users input their impressions and evaluations of the provided content and send them from their devices to the server. This feedback information plays a crucial role in the optimization process for generating future schedules and content lists.

[0315] As a concrete example, consider the presentation of content at a music festival. Based on data from artists the user has watched in the past, they are recommended appropriate live performances from artists scheduled to participate in the next festival. In this case, an example of a prompt would be, "Based on the user's past viewing history, please suggest new live videos this week that might be of particular interest to them."

[0316] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0317] Step 1:

[0318] The server collects participants' past behavioral data from a cloud database. The input is behavioral data stored in cloud storage, and the output is a dataset for analysis. This dataset integrates information including participants' past choices and interests.

[0319] Step 2:

[0320] The server analyzes the collected dataset using a generative AI model. The input is the dataset from Step 1, and the output is a timetable optimized for each participant. The AI ​​model analyzes patterns in the data and identifies the content and activities that best match the participants' interests.

[0321] Step 3:

[0322] The server sends the generated timetable to the participants' information terminals via the cloud. The input here is the timetable generated in step 2, and the output is a visual display of the timetable on the terminal. The information terminal displays this timetable in its user interface, making it easy for participants to check.

[0323] Step 4:

[0324] The user reviews a list of content presented through a visual display device and selects content of interest. The input is the content list displayed on the terminal, and the output is information about the selected content. This selection information is transmitted from the visual display device to the terminal and synchronized for the next step.

[0325] Step 5:

[0326] The terminal synchronizes the content information selected by the user to a cloud database. The input is the content information selected in step 4, and the output is the synchronization status to the information storage device. The cloud database receives this and uses it as data to interact with other devices.

[0327] Step 6:

[0328] Users input their thoughts and evaluations of the content from their devices and send them to the server. The input consists of user evaluation comments and feedback data, while the output is a feedback record used in the next optimization process. The server stores this feedback information and incorporates it into the next timetable generation.

[0329] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0330] This invention provides a system that offers an event schedule based on participants' interests and combines it with an emotion engine that recognizes users' emotions. The system aims to provide participants with a more highly personalized event experience.

[0331] This system primarily consists of four components: a server, a terminal, a user, and an emotion engine. First, the server collects past behavioral data from participants and stores it in a database. This data includes events the participant has previously attended, topics they have shown interest in, and their ratings. Based on the collected data, the server uses a generative model to analyze the data and generate an optimized event schedule for each participant.

[0332] The generated schedule is sent from the server to each participant's device and displayed on their device. Users can review this schedule and make manual adjustments as needed. The adjusted schedule is sent to the server in real time and kept up-to-date on the server.

[0333] A distinctive component of this invention is an emotion engine. The emotion engine recognizes emotions in real time from the user's facial expressions, tone of voice, and other factors. This information is used by the server to optimize the schedule. For example, if a user shows positive emotions towards a particular activity, the server will set a higher priority for that activity. If a user shows negative emotions, the server can suggest alternative activities and automatically restructure the schedule.

[0334] For example, if the emotion engine detects many positive emotions from a user on the first day of an exhibition, the server will present a schedule for the second day that reflects an increase in activities similar to those of that user. Conversely, for sessions with negative ratings, similar activities can be removed to improve the overall experience. In this way, the system can incorporate real-time emotion information from users and provide an event experience optimized for participants.

[0335] The following describes the processing flow.

[0336] Step 1:

[0337] The server collects past behavioral data from event participants and stores it in a database. This includes detailed information such as the activities they participated in and the topics they showed interest in.

[0338] Step 2:

[0339] The server uses a generative model to analyze the collected behavioral data. This generates an optimized event schedule for each participant, creating a schedule tailored to individual interests.

[0340] Step 3:

[0341] The server sends the generated schedule to the participants' devices. The devices then visually display this schedule to the users and prompt them for confirmation.

[0342] Step 4:

[0343] Users check the schedule displayed on their device and make manual adjustments as needed. These adjustments include changing the priority of activities they want to participate in and rearranging the times.

[0344] Step 5:

[0345] The terminal sends the user's adjustments to the server in real time, and the latest information is managed on the server.

[0346] Step 6:

[0347] The emotion engine recognizes the user's facial expressions and voice tone in real time and generates emotion data. This emotion data is categorized into positive, negative, neutral, and other categories.

[0348] Step 7:

[0349] The server re-evaluates the schedule based on the emotion data received from the emotion engine. If the emotion is positive, it prioritizes the relevant activity; if the emotion is negative, it suggests an alternative activity.

[0350] Step 8:

[0351] The device notifies the user of the re-evaluated schedule and presents a new schedule that reflects the suggestions.

[0352] Step 9:

[0353] After the event ends, users enter feedback from their devices and send it to the server. This feedback data is used to generate future event schedules and is reflected in the analysis results.

[0354] (Example 2)

[0355] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0356] Current event scheduling systems have the challenge of making it difficult to provide an experience optimized for each individual participant. Specifically, they cannot reflect participants' individual interests and emotions in real time, and are limited to providing an experience based on a fixed schedule. As a result, it becomes difficult to improve participant satisfaction.

[0357] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0358] In this invention, the server includes means for collecting information on participants' past behavior and storing it in an information storage medium; means for analyzing the participants' past behavior information using a generative model and generating an optimal activity schedule for each participant; and means for analyzing the characteristics of participants' facial expressions and voices and acquiring emotional information. This makes it possible to provide an optimized activity schedule in real time according to the participants' interests and emotions.

[0359] "Participants" refers to individual users involved in an event or activity.

[0360] "Past behavioral information" refers to data about events participants have previously attended, their interests, and their evaluations.

[0361] An "information storage medium" refers to a storage device used to accumulate and manage data.

[0362] A "generative model" refers to an algorithm or method used to analyze data and generate specific deliverables.

[0363] "Activity schedule" refers to a schedule outlining the events and activities that participants will be taking part in in the future.

[0364] "Information terminal" refers to an electronic device used by participants to receive, view, or manipulate information.

[0365] "Facial and vocal characteristics" refers to visual or auditory information obtained from the participants' facial expressions and speech.

[0366] "Emotional information" refers to data that indicates the emotional state of participants.

[0367] Prioritization refers to the act of assigning relative importance to a series of items or tasks.

[0368] "Evaluation information" refers to data that shows the opinions and impressions that participants have about their experiences and activities.

[0369] To implement this invention, a system consisting mainly of a server, terminal, user, and emotion engine is constructed.

[0370] The server acts as the central hub, collecting and processing information about the past behavior of participating users. This includes events the user has previously attended, topics they have shown interest in, and their ratings. A common database management system can be used to store this data. Furthermore, the server uses a generative AI model to analyze this data and create an activity schedule optimized for the user. This process can utilize programming languages ​​such as Python or machine learning libraries such as TensorFlow.

[0371] The terminal functions as a device for users to check their activity schedule and edit it as needed. Schedules sent from the server are displayed on the terminal. Users can adjust their schedules on this terminal, and these adjustments are immediately sent to the server. The HTTP protocol could be used for this.

[0372] Furthermore, this invention includes an emotion engine. The emotion engine acquires emotional information from the user's facial expressions and voice. This information is collected using a camera and microphone and analyzed using OpenCV or other speech recognition technologies. Based on this emotional information, the server can further personalize the user's schedule.

[0373] For example, if a user expresses positive emotions through the emotion engine on the first day of an exhibition, the server will generate a schedule for the second day that includes similar activities. Conversely, for sessions that receive negative ratings, similar content can be removed, and the schedule can be reorganized to provide a better experience.

[0374] An example of a prompt message is, "Generate an optimal schedule based on the user's preferred activities and readjust it to reflect sentiment data." This allows the system to provide a more personalized activity experience optimized for the participant.

[0375] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0376] Step 1:

[0377] The server collects information about the user's past behavior and stores it in a data storage medium. Specifically, it obtains data such as events the user has previously participated in, topics they are interested in, and ratings through APIs and log files. This input data is stored in a structured format using a database management system.

[0378] Step 2:

[0379] The server performs data analysis using a generative AI model based on collected past behavioral information. This analysis extracts user interests and tendencies and generates an optimal activity plan. Here, behavioral information stored in the database is taken as input, and a predicted activity plan is obtained as output. Statistical calculations are performed using a machine learning framework.

[0380] Step 3:

[0381] The server sends the generated activity schedule to the user's terminal. This process uses the HTTP protocol to send the schedule information to the terminal in JSON format. The terminal receives this data as input and displays the schedule in the user interface.

[0382] Step 4:

[0383] Users review their activity schedule displayed on their device and make adjustments as needed. Specifically, they can change, add, or delete appointments using drag-and-drop functionality or selection buttons. This adjusted schedule is then resent from the device to the server, where it is updated to the latest state.

[0384] Step 5:

[0385] The emotion engine analyzes the user's facial expressions and voice tone in real time to acquire emotional information. It inputs data using a camera and microphone, and converts it into emotional information using OpenCV and speech recognition technology. This information generates output indicating the user's current emotional state.

[0386] Step 6:

[0387] The server uses the acquired sentiment information to automatically readjust the activity schedule. It receives sentiment information as input, prioritizes activities that elicit positive emotions from the user, and suggests alternatives for activities that receive negative ratings. This readjusted schedule is then generated and sent back to the device.

[0388] (Application Example 2)

[0389] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0390] Modern commercial facilities and event venues are required to provide visitors with personalized experiences. Traditional methods struggle to deliver the optimal experience tailored to participants' interests and lack the ability to dynamically adjust in real time to reflect emotions and interests. In particular, there is a need to quickly reflect collected emotional information and individually optimize the visitor experience.

[0391] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0392] In this invention, the server includes means for collecting and storing past behavioral data of participants in a database, means for analyzing past behavioral data of participants using a generative model and generating an optimal event plan for each participant, and means for acquiring participants' emotional information in real time and dynamically optimizing the event plan using that information. This makes it possible to provide a personalized experience based on participants' past behavior and real-time emotions, thereby improving visitor satisfaction.

[0393] "Participants" are individuals who visit a specific event or commercial facility.

[0394] "Behavioral data" refers to a collection of information about the actions and choices that participants have made in the past.

[0395] A "database" is a system that stores data and enables efficient management and retrieval.

[0396] A "generative model" is an algorithm that analyzes participants' behavioral data and generates results tailored to a specific purpose.

[0397] An "event plan" is a proposed schedule that optimizes the events and activities that participants will experience.

[0398] "Information processing equipment" refers to electronic devices such as mobile terminals and computers used by participants.

[0399] "Emotional information" refers to data about the emotional state obtained from participants' facial expressions and voice.

[0400] "Dynamic optimization" is a process of immediately adjusting plans and proposals based on real-time information.

[0401] "Evaluation information" refers to data that includes opinions and impressions of participants' experiences.

[0402] The system that realizes this invention consists of a server, terminals, users, and an emotion engine that complements them. The server accesses a database to collect and store past behavioral data of participants and analyzes it using a generative model to generate an optimized event plan for each participant. This makes it possible to personalize events based on participants' past interests and behaviors.

[0403] The generated event plan is transmitted via the internet to participants' information processing devices (e.g., smartphones, tablets). The devices display the received information, allowing participants to review and adjust the plan based on this information. This adjustment information is then sent back to the server and updated in real time.

[0404] The emotion engine collects user facial expressions via camera and audio via microphone, extracting emotional information in real time. Specifically, it performs image analysis using OpenCV and DeepFace, converts audio to text using the Google Cloud Speech-to-Text API, and then evaluates emotions using natural language processing techniques. This allows the system to dynamically adjust plans according to the user's emotions, providing a better experience.

[0405] For example, when a user is searching for products in a store, if their facial expression is positively recognized by their smartphone camera, the server can prioritize suggesting products from a specific brand. Conversely, if there is a negative reaction, the server will refrain from suggesting related products.

[0406] An example of a prompt to input into the generating AI model is: "Identify in real time what products the user is interested in in a physical store, and consider how to present the most suitable offers and information for that day." This prompt is used to generate a scenario that personalizes product suggestions for the user.

[0407] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0408] Step 1:

[0409] The server collects past behavioral data from participants from a database. Inputs include past behavioral records, topics of interest, and evaluation data. Based on this data, the server organizes and integrates the participants' past history and prepares it for analysis.

[0410] Step 2:

[0411] The server uses the collected behavioral data to launch a generative model and perform analysis. The input is behavioral data, and the generative AI model is used to analyze behavioral patterns and their correlations. As output, an event plan optimized for each participant is generated.

[0412] Step 3:

[0413] The server sends the generated event plan to the participants' terminals via the internet. The terminals receive this event plan internally and display it visually on their screens. The input here is the event plan data, and the output is what is displayed on the terminals.

[0414] Step 4:

[0415] Users view the event schedule displayed on their terminal and make adjustments as needed. Users input requests such as desired destinations and time slots. The terminal receives this information and resends it to the server, updating the schedule.

[0416] Step 5:

[0417] The emotion engine captures the user's facial expressions with a camera and records their voice with a microphone. The input consists of the user's real-time facial expressions and voice. OpenCV and the Google Cloud Speech-to-Text API are used to extract this data as emotional information. The output is a positive or negative emotional evaluation.

[0418] Step 6:

[0419] The server dynamically optimizes event plans using emotion information received in real time. Inputs are emotion information and existing event plans, and the system uses a generative AI model to adjust the plans. The output is an updated event plan based on the emotions.

[0420] Step 7:

[0421] The terminal receives the updated event plan again from the server and presents it to the user. The final output is a display of the optimized event plan, with an example prompt message being, "Identify in real time what products the user is interested in in-store and consider how to present the most suitable offers and information for that day."

[0422] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0423] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0424] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0425] [Third Embodiment]

[0426] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0427] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0428] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0429] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0430] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0431] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0432] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0433] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0434] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0435] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0436] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0437] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0438] This invention is a system for providing event participants with an optimal event schedule tailored to their individual interests. This system consists of three components: a server, a terminal, and a user.

[0439] First, the server collects past behavioral data from participants. This behavioral data is based on participants' past participation activities and interests in events. This data is stored in a database on the server and can be retrieved as needed.

[0440] Next, the server uses the accumulated data to perform analysis through a generative model. The generative model analyzes participants' past behavioral patterns and generates an optimal schedule based on each participant's interests. The generated schedule is prioritized and designed so that users can participate in the activities that interest them most first.

[0441] The generated schedule is sent from the server to each participant's terminal. The terminal provides an interface to visually present the received schedule to the user. The user can review the provided schedule and make adjustments according to their interests.

[0442] For example, if a user prioritizes a particular activity, they can adjust the time for that activity on the schedule displayed on their device. Once the schedule is adjusted, the device resends it to the server to maintain its current state.

[0443] Furthermore, users can share the generated schedule with other participants. This provides an easy way for participants with similar interests to interact. After participating, users enter feedback about their event experience on their device and send it to the server. This feedback helps improve the accuracy of schedule generation for future events.

[0444] In this way, this system provides schedules optimized to each user's preferences, promotes interaction among participants, and enhances the event participation experience.

[0445] The following describes the processing flow.

[0446] Step 1:

[0447] The server collects past behavioral data from event participants. This includes activities they participated in, their ratings, and topics of interest, and stores this data in a database.

[0448] Step 2:

[0449] The server uses a generative model to analyze the interests of each participant based on the collected data. This generates an event schedule optimized for each participant.

[0450] Step 3:

[0451] The server sends the generated schedule to each participant's device. The device then displays the received schedule in its user interface, providing it visually.

[0452] Step 4:

[0453] Users can check their schedules on their devices and manually adjust them as needed. For example, they can delete lower-priority events or adjust their times.

[0454] Step 5:

[0455] The terminal sends the user's schedule adjustments to the server in real time. The server manages the latest schedule and synchronizes schedules with other participants as needed.

[0456] Step 6:

[0457] Users can share their schedules with other participants. In this process, the device generates a sharing link and exchanges schedule information.

[0458] Step 7:

[0459] After the event ends, users enter feedback from their devices and send it to the server. The server stores this feedback data in a database and uses it to generate the schedule for the next event.

[0460] (Example 1)

[0461] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0462] In today's diverse world of events, it is crucial to provide participants with optimal event schedules tailored to their individual interests and past behavioral patterns. However, conventional schedule provision systems struggle to adequately consider the individuality of each participant. Specifically, for events with many participants attending simultaneously, there is a need for an efficient and effective system that automatically adjusts schedules to reflect each individual's interests and presents the results quickly.

[0463] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0464] In this invention, the server includes means for aggregating participants' past activity data and storing it in an information storage device, means for analyzing participants' past activity data using a generation algorithm and generating an optimal event schedule for each participant, and means for transmitting and displaying the generated event schedule to the participants' communication devices. This makes it possible to create flexible schedules that reflect the interests of individual participants.

[0465] "Participants" refers to individuals or people who participate in activities or events within a given event.

[0466] "Activity data" refers to information about participants' past event participation history and behavioral patterns based on their interests.

[0467] An "information storage device" refers to a device that has the function of systematically storing data and allowing it to be referenced as needed.

[0468] A "generative algorithm" refers to a computational method used to analyze participant activity data and derive the optimal event schedule.

[0469] "Event schedule" refers to a schedule that shows the times and order of events and activities that participants can take part in.

[0470] "Communication device" refers to an electronic device used to send and receive information to and from participants.

[0471] The system in this invention is an advanced technology that generates an optimal event schedule based on participants' interests. To implement the invention, the system mainly consists of three entities: a "server," a "terminal," and a "user." Each entity plays a specific role, and the system functions effectively by coordinating with each other as a whole.

[0472] First, the server collects participants' past activity data and stores it in an information storage device. This information storage device is implemented in a format such as an SQL database, efficiently managing participants' past event participation history and interest data. The server also uses a generation algorithm to analyze participants' activity data and generate an optimal event schedule for each participant. A widely used machine learning model can be applied as the generation algorithm, enabling the generation of schedules that take into account the different interests and preferences of participants.

[0473] Next, the server transmits the generated event schedule to the participants' communication devices, i.e., terminals. The terminals provide an interface for visually presenting this schedule to the users. Specifically, the terminals receive the data and display it visually through the user interface in a way that is intuitively easy for participants to understand.

[0474] Users can use the terminal interface to review the presented event schedule and make adjustments according to their interests and convenience. For example, if they want to prioritize a particular activity, they can change the time of that activity on the terminal. The adjusted event schedule is then sent back to the server and recorded as the latest state in the server's information storage device. This ensures that participants have the optimal experience according to the time.

[0475] As a concrete example of such a system, if a participant is interested in art, the server considers that participant's past participation history in art-related events and prioritizes scheduling museum visits, painting workshops, and similar activities. This allows participants to attend events that best match their interests.

[0476] As an example of a prompt in a generative AI model, the instructions the system receives might be the following text:

[0477] "Based on participants' past activity data, generate an optimal event schedule. Prioritize activities that will pique their interest and propose a visually clear and easy-to-understand format for displaying the schedule on their devices."

[0478] This prompt allows the system to leverage its technical advantages to design an event experience that aligns with the individual needs of each participant.

[0479] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0480] Step 1:

[0481] The server collects data on participants' past activities.

[0482] The system acquires data such as event participation history and areas of interest as input, and stores this data in an information storage device on the server. Specifically, the server retrieves data from various sources, organizes it in an SQL database, and stores it. This creates a comprehensive profile of the participant's preferences and interests.

[0483] Step 2:

[0484] The server uses a generated AI model to analyze the collected activity data.

[0485] The server receives accumulated data as input and prompts the generating AI model to perform analysis. Specifically, the AI ​​model analyzes the participants' past behavioral patterns and generates an optimal event schedule for each participant. This process utilizes machine learning algorithms, and the output is a prioritized event schedule.

[0486] Step 3:

[0487] The server sends the generated event schedule to the terminal.

[0488] The event schedule generated by the AI ​​model is used as input, and the server converts it into JSON format and transmits it to the terminal. Specifically, data is transferred from the server to the terminal using the HTTP protocol, and the terminal receives it. This prepares the event information that is most suitable for the participant.

[0489] Step 4:

[0490] The terminal visually displays the received event schedule to the user.

[0491] The event schedule received from the server is used as input, and the terminal provides an interface to visually display it. Specifically, a graphical user interface is used to display the schedule and activity details on the screen. This makes it easier for the user to intuitively understand the event schedule.

[0492] Step 5:

[0493] The user reviews the presented schedule and makes adjustments as needed.

[0494] The input is an event schedule displayed on the device, and the user adjusts the schedule through drag-and-drop and other methods. Specifically, it is possible to select activities that are prioritized and change their time and order. This operation enables the customization of the schedule to suit the user's individual interests.

[0495] Step 6:

[0496] The terminal resends the adjusted schedule to the server.

[0497] The event schedule, modified by the user, is used as input, and the terminal sends it back to the server in JSON format. In the actual processing, the server records this data again in the information storage device, keeping it up-to-date. This ensures that participants' schedules are always managed based on the latest information.

[0498] (Application Example 1)

[0499] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0500] Existing content distribution services face the challenge of efficiently providing content tailored to user interests. In particular, they lack sufficient individualized support that leverages the characteristics of visual display devices, limiting the user experience. Therefore, there is a need for more personalized content presentation and scheduling based on user interests and behavioral patterns.

[0501] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0502] In this invention, the server includes means for collecting past behavioral data of participants and storing it in an information storage device; means for analyzing past behavioral data of participants using a generation model and generating an optimal timetable for each participant; means for transmitting and displaying the generated timetable on the participant's information terminal; means for presenting a content list to participants using a visual display device; means for synchronizing selected content from the content list with the information storage device and coordinating information with other devices; and means for collecting participants' feedback or evaluation information and reflecting it in the generation of the next timetable. This enables individually optimized display of content according to user interests, as well as real-time synchronization and adjustment of information.

[0503] A "participant" is a user of the service within the system and the entity that provides information about their individual actions.

[0504] "Behavioral data" refers to information that records the choices and activities that participants have made in the past, and it is the data that forms the basis of the analysis.

[0505] An "information storage device" is a storage medium within a system that stores accumulated behavioral data and generated timetables.

[0506] A "generative model" is a mathematical or algorithmic computational method used to analyze past behavioral data.

[0507] A "timetable" is a plan or schedule created to guide participants' activities based on the analysis results.

[0508] An "information terminal" is an electronic device used by participants to access the system's functions.

[0509] A "visual display device" is a display device used to provide information to participants visually, and includes glasses-type devices.

[0510] A "content list" is a list of information or media items selected based on the participants' interests.

[0511] "Information sharing" refers to the act of synchronizing or sharing data between multiple devices.

[0512] "Feedback or evaluation information" refers to the subjective evaluations that participants give to content or services, and this data is used to optimize future offerings.

[0513] The system realizing this invention utilizes various devices and software to deliver and schedule optimal content based on participants' interests. The main components are a server, an information terminal, and a visual display device.

[0514] The server collects and stores participants' past behavioral data using an information storage device. A cloud database such as Firebase is used for this purpose. Next, a generative AI model such as TensorFlow is used to analyze the collected behavioral data and generate a personalized schedule based on the participants' interests. The generated schedule is then sent to the participants' information terminals via the cloud service.

[0515] Participants' information terminals will use Flutter or similar tools to build a user interface and display the generated timetable. Visual display devices, such as glasses (Google Glass, for example), will present users with a list of content in real time, and users will select content of interest from that list. The selected content will be synchronized via Firebase, maintaining information sharing with other devices.

[0516] Furthermore, users input their impressions and evaluations of the provided content and send them from their devices to the server. This feedback information plays a crucial role in the optimization process for generating future schedules and content lists.

[0517] As a concrete example, consider the presentation of content at a music festival. Based on data from artists the user has watched in the past, they are recommended appropriate live performances from artists scheduled to participate in the next festival. In this case, an example of a prompt would be, "Based on the user's past viewing history, please suggest new live videos this week that might be of particular interest to them."

[0518] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0519] Step 1:

[0520] The server collects participants' past behavioral data from a cloud database. The input is behavioral data stored in cloud storage, and the output is a dataset for analysis. This dataset integrates information including participants' past choices and interests.

[0521] Step 2:

[0522] The server analyzes the collected dataset using a generative AI model. The input is the dataset from Step 1, and the output is a timetable optimized for each participant. The AI ​​model analyzes patterns in the data and identifies the content and activities that best match the participants' interests.

[0523] Step 3:

[0524] The server sends the generated timetable to the participants' information terminals via the cloud. The input here is the timetable generated in step 2, and the output is a visual display of the timetable on the terminal. The information terminal displays this timetable in its user interface, making it easy for participants to check.

[0525] Step 4:

[0526] The user reviews a list of content presented through a visual display device and selects content of interest. The input is the content list displayed on the terminal, and the output is information about the selected content. This selection information is transmitted from the visual display device to the terminal and synchronized for the next step.

[0527] Step 5:

[0528] The terminal synchronizes the content information selected by the user to a cloud database. The input is the content information selected in step 4, and the output is the synchronization status to the information storage device. The cloud database receives this and uses it as data to interact with other devices.

[0529] Step 6:

[0530] Users input their thoughts and evaluations of the content from their devices and send them to the server. The input consists of user evaluation comments and feedback data, while the output is a feedback record used in the next optimization process. The server stores this feedback information and incorporates it into the next timetable generation.

[0531] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0532] This invention provides a system that offers an event schedule based on participants' interests and combines it with an emotion engine that recognizes users' emotions. The system aims to provide participants with a more highly personalized event experience.

[0533] This system primarily consists of four components: a server, a terminal, a user, and an emotion engine. First, the server collects past behavioral data from participants and stores it in a database. This data includes events the participant has previously attended, topics they have shown interest in, and their ratings. Based on the collected data, the server uses a generative model to analyze the data and generate an optimized event schedule for each participant.

[0534] The generated schedule is sent from the server to each participant's device and displayed on their device. Users can review this schedule and make manual adjustments as needed. The adjusted schedule is sent to the server in real time and kept up-to-date on the server.

[0535] A distinctive component of this invention is an emotion engine. The emotion engine recognizes emotions in real time from the user's facial expressions, tone of voice, and other factors. This information is used by the server to optimize the schedule. For example, if a user shows positive emotions towards a particular activity, the server will set a higher priority for that activity. If a user shows negative emotions, the server can suggest alternative activities and automatically restructure the schedule.

[0536] For example, if the emotion engine detects many positive emotions from a user on the first day of an exhibition, the server will present a schedule for the second day that reflects an increase in activities similar to those of that user. Conversely, for sessions with negative ratings, similar activities can be removed to improve the overall experience. In this way, the system can incorporate real-time emotion information from users and provide an event experience optimized for participants.

[0537] The following describes the processing flow.

[0538] Step 1:

[0539] The server collects past behavioral data from event participants and stores it in a database. This includes detailed information such as the activities they participated in and the topics they showed interest in.

[0540] Step 2:

[0541] The server uses a generative model to analyze the collected behavioral data. This generates an optimized event schedule for each participant, creating a schedule tailored to individual interests.

[0542] Step 3:

[0543] The server sends the generated schedule to the participants' devices. The devices then visually display this schedule to the users and prompt them for confirmation.

[0544] Step 4:

[0545] Users check the schedule displayed on their device and make manual adjustments as needed. These adjustments include changing the priority of activities they want to participate in and rearranging the times.

[0546] Step 5:

[0547] The terminal sends the user's adjustments to the server in real time, and the latest information is managed on the server.

[0548] Step 6:

[0549] The emotion engine recognizes the user's facial expressions and voice tone in real time and generates emotion data. This emotion data is categorized into positive, negative, neutral, and other categories.

[0550] Step 7:

[0551] The server re-evaluates the schedule based on the emotion data received from the emotion engine. If the emotion is positive, it prioritizes the relevant activity; if the emotion is negative, it suggests an alternative activity.

[0552] Step 8:

[0553] The device notifies the user of the re-evaluated schedule and presents a new schedule that reflects the suggestions.

[0554] Step 9:

[0555] After the event ends, users enter feedback from their devices and send it to the server. This feedback data is used to generate future event schedules and is reflected in the analysis results.

[0556] (Example 2)

[0557] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0558] Current event scheduling systems have the challenge of making it difficult to provide an experience optimized for each individual participant. Specifically, they cannot reflect participants' individual interests and emotions in real time, and are limited to providing an experience based on a fixed schedule. As a result, it becomes difficult to improve participant satisfaction.

[0559] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0560] In this invention, the server includes means for collecting information on participants' past behavior and storing it in an information storage medium; means for analyzing the participants' past behavior information using a generative model and generating an optimal activity schedule for each participant; and means for analyzing the characteristics of participants' facial expressions and voices and acquiring emotional information. This makes it possible to provide an optimized activity schedule in real time according to the participants' interests and emotions.

[0561] "Participants" refers to individual users involved in an event or activity.

[0562] "Past behavioral information" refers to data about events participants have previously attended, their interests, and their evaluations.

[0563] An "information storage medium" refers to a storage device used to accumulate and manage data.

[0564] A "generative model" refers to an algorithm or method used to analyze data and generate specific deliverables.

[0565] "Activity schedule" refers to a schedule outlining the events and activities that participants will be taking part in in the future.

[0566] "Information terminal" refers to an electronic device used by participants to receive, view, or manipulate information.

[0567] "Facial and vocal characteristics" refers to visual or auditory information obtained from the participants' facial expressions and speech.

[0568] "Emotional information" refers to data that indicates the emotional state of participants.

[0569] Prioritization refers to the act of assigning relative importance to a series of items or tasks.

[0570] "Evaluation information" refers to data that shows the opinions and impressions that participants have about their experiences and activities.

[0571] To implement this invention, a system consisting mainly of a server, terminal, user, and emotion engine is constructed.

[0572] The server acts as the central hub, collecting and processing information about the past behavior of participating users. This includes events the user has previously attended, topics they have shown interest in, and their ratings. A common database management system can be used to store this data. Furthermore, the server uses a generative AI model to analyze this data and create an activity schedule optimized for the user. This process can utilize programming languages ​​such as Python or machine learning libraries such as TensorFlow.

[0573] The terminal functions as a device for users to check their activity schedule and edit it as needed. Schedules sent from the server are displayed on the terminal. Users can adjust their schedules on this terminal, and these adjustments are immediately sent to the server. The HTTP protocol could be used for this.

[0574] Furthermore, this invention includes an emotion engine. The emotion engine acquires emotional information from the user's facial expressions and voice. This information is collected using a camera and microphone and analyzed using OpenCV or other speech recognition technologies. Based on this emotional information, the server can further personalize the user's schedule.

[0575] For example, if a user expresses positive emotions through the emotion engine on the first day of an exhibition, the server will generate a schedule for the second day that includes similar activities. Conversely, for sessions that receive negative ratings, similar content can be removed, and the schedule can be reorganized to provide a better experience.

[0576] An example of a prompt message is, "Generate an optimal schedule based on the user's preferred activities and readjust it to reflect sentiment data." This allows the system to provide participants with a more personalized and optimized activity experience.

[0577] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0578] Step 1:

[0579] The server collects information about the user's past behavior and stores it in a data storage medium. Specifically, it obtains data such as events the user has previously participated in, topics they are interested in, and ratings through APIs and log files. This input data is stored in a structured format using a database management system.

[0580] Step 2:

[0581] The server performs data analysis using a generative AI model based on collected past behavioral information. This analysis extracts user interests and tendencies and generates an optimal activity plan. Here, behavioral information stored in the database is taken as input, and a predicted activity plan is obtained as output. Statistical calculations are performed using a machine learning framework.

[0582] Step 3:

[0583] The server sends the generated activity schedule to the user's terminal. This process uses the HTTP protocol to send the schedule information to the terminal in JSON format. The terminal receives this data as input and displays the schedule in the user interface.

[0584] Step 4:

[0585] Users review their activity schedule displayed on their device and make adjustments as needed. Specifically, they can change, add, or delete appointments using drag-and-drop functionality or selection buttons. This adjusted schedule is then resent from the device to the server, where it is updated to the latest state.

[0586] Step 5:

[0587] The emotion engine analyzes the user's facial expressions and voice tone in real time to acquire emotional information. It takes data from a camera and microphone as input and converts it into emotional information using OpenCV and speech recognition technology. This information generates output indicating the user's current emotional state.

[0588] Step 6:

[0589] The server uses the acquired sentiment information to automatically readjust the activity schedule. It receives sentiment information as input, prioritizes activities that elicit positive emotions from the user, and suggests alternatives for activities that receive negative ratings. This readjusted schedule is then generated and sent back to the device.

[0590] (Application Example 2)

[0591] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0592] Modern commercial facilities and event venues are required to provide visitors with personalized experiences. Traditional methods struggle to deliver the optimal experience tailored to participants' interests and lack the ability to dynamically adjust in real time to reflect emotions and interests. In particular, there is a need to quickly reflect collected emotional information and individually optimize the visitor experience.

[0593] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0594] In this invention, the server includes means for collecting and storing past behavioral data of participants in a database, means for analyzing past behavioral data of participants using a generative model and generating an optimal event plan for each participant, and means for acquiring participants' emotional information in real time and dynamically optimizing the event plan using that information. This makes it possible to provide a personalized experience based on participants' past behavior and real-time emotions, thereby improving visitor satisfaction.

[0595] "Participants" are individuals who visit a specific event or commercial facility.

[0596] "Behavioral data" refers to a collection of information about the actions and choices that participants have made in the past.

[0597] A "database" is a system that stores data and enables efficient management and retrieval.

[0598] A "generative model" is an algorithm that analyzes participants' behavioral data and generates results tailored to a specific purpose.

[0599] An "event plan" is a proposed schedule that optimizes the events and activities that participants will experience.

[0600] "Information processing equipment" refers to electronic devices such as mobile terminals and computers used by participants.

[0601] "Emotional information" refers to data about the emotional state obtained from participants' facial expressions and voice.

[0602] "Dynamic optimization" is a process of immediately adjusting plans and proposals based on real-time information.

[0603] "Evaluation information" refers to data that includes opinions and impressions of participants' experiences.

[0604] The system that realizes this invention consists of a server, terminals, users, and an emotion engine that complements them. The server accesses a database to collect and store past behavioral data of participants and analyzes it using a generative model to generate an optimized event plan for each participant. This makes it possible to personalize events based on participants' past interests and behaviors.

[0605] The generated event plan is transmitted via the internet to participants' information processing devices (e.g., smartphones, tablets). The devices display the received information, allowing participants to review and adjust the plan based on this information. This adjustment information is then sent back to the server and updated in real time.

[0606] The emotion engine collects user facial expressions via camera and audio via microphone, extracting emotional information in real time. Specifically, it performs image analysis using OpenCV and DeepFace, converts audio to text using the Google Cloud Speech-to-Text API, and then evaluates emotions using natural language processing techniques. This allows the system to dynamically adjust plans according to the user's emotions, providing a better experience.

[0607] For example, when a user is searching for products in a store, if their facial expression is positively recognized by their smartphone camera, the server can prioritize suggesting products from a specific brand. Conversely, if there is a negative reaction, the server will refrain from suggesting related products.

[0608] An example of a prompt to input into the generating AI model is: "Identify in real time what products the user is interested in in a physical store, and consider how to present the most suitable offers and information for that day." This prompt is used to generate a scenario that personalizes product suggestions for the user.

[0609] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0610] Step 1:

[0611] The server collects past behavioral data from participants from a database. Inputs include past behavioral records, topics of interest, and evaluation data. Based on this data, the server organizes and integrates the participants' past history and prepares it for analysis.

[0612] Step 2:

[0613] The server uses the collected behavioral data to launch a generative model and perform analysis. The input is behavioral data, and the generative AI model is used to analyze behavioral patterns and their correlations. As output, an event plan optimized for each participant is generated.

[0614] Step 3:

[0615] The server sends the generated event plan to the participants' terminals via the internet. The terminals receive this event plan internally and display it visually on their screens. The input here is the event plan data, and the output is what is displayed on the terminals.

[0616] Step 4:

[0617] Users view the event schedule displayed on their terminal and make adjustments as needed. Users input requests such as desired destinations and time slots. The terminal receives this information and resends it to the server, updating the schedule.

[0618] Step 5:

[0619] The emotion engine captures the user's facial expressions with a camera and records their voice with a microphone. The input consists of the user's real-time facial expressions and voice. OpenCV and the Google Cloud Speech-to-Text API are used to extract this data as emotional information. The output is a positive or negative emotional evaluation.

[0620] Step 6:

[0621] The server dynamically optimizes event plans using emotion information received in real time. Inputs are emotion information and existing event plans, and the system uses a generative AI model to adjust the plans. The output is an updated event plan based on the emotions.

[0622] Step 7:

[0623] The terminal receives the updated event plan again from the server and presents it to the user. The final output is a display of the optimized event plan, with an example prompt message being, "Identify in real time what products the user is interested in in-store and consider how to present the most suitable offers and information for that day."

[0624] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0625] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0626] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0627] [Fourth Embodiment]

[0628] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0629] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0630] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0631] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0632] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0633] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0634] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0635] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0636] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0637] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0638] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0639] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0640] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0641] This invention is a system for providing event participants with an optimal event schedule tailored to their individual interests. This system consists of three components: a server, a terminal, and a user.

[0642] First, the server collects past behavioral data from participants. This behavioral data is based on participants' past participation activities and interests in events. This data is stored in a database on the server and can be retrieved as needed.

[0643] Next, the server uses the accumulated data to perform analysis through a generative model. The generative model analyzes participants' past behavioral patterns and generates an optimal schedule based on each participant's interests. The generated schedule is prioritized and designed so that users can participate in the activities that interest them most first.

[0644] The generated schedule is sent from the server to each participant's terminal. The terminal provides an interface to visually present the received schedule to the user. The user can review the provided schedule and make adjustments according to their interests.

[0645] For example, if a user prioritizes a particular activity, they can adjust the time for that activity on the schedule displayed on their device. Once the schedule is adjusted, the device resends it to the server to maintain its current state.

[0646] Furthermore, users can share the generated schedule with other participants. This provides an easy way for participants with similar interests to interact. After participating, users enter feedback about their event experience on their device and send it to the server. This feedback helps improve the accuracy of schedule generation for future events.

[0647] In this way, this system provides schedules optimized to each user's preferences, promotes interaction among participants, and enhances the event participation experience.

[0648] The following describes the processing flow.

[0649] Step 1:

[0650] The server collects past behavioral data from event participants. This includes activities they participated in, their ratings, and topics of interest, and stores this data in a database.

[0651] Step 2:

[0652] The server uses a generative model to analyze the interests of each participant based on the collected data. This generates an event schedule optimized for each participant.

[0653] Step 3:

[0654] The server sends the generated schedule to each participant's device. The device then displays the received schedule in its user interface, providing it visually.

[0655] Step 4:

[0656] Users can check their schedules on their devices and manually adjust them as needed. For example, they can delete lower-priority events or adjust their times.

[0657] Step 5:

[0658] The terminal sends the user's schedule adjustments to the server in real time. The server manages the latest schedule and synchronizes schedules with other participants as needed.

[0659] Step 6:

[0660] Users can share their schedules with other participants. In this process, the device generates a sharing link and exchanges schedule information.

[0661] Step 7:

[0662] After the event ends, users enter feedback from their devices and send it to the server. The server stores this feedback data in a database and uses it to generate the schedule for the next event.

[0663] (Example 1)

[0664] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0665] In today's diverse world of events, it is crucial to provide participants with optimal event schedules tailored to their individual interests and past behavioral patterns. However, conventional schedule provision systems struggle to adequately consider the individuality of each participant. Specifically, for events with many participants attending simultaneously, there is a need for an efficient and effective system that automatically adjusts schedules to reflect each individual's interests and presents the results quickly.

[0666] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0667] In this invention, the server includes means for aggregating participants' past activity data and storing it in an information storage device, means for analyzing participants' past activity data using a generation algorithm and generating an optimal event schedule for each participant, and means for transmitting and displaying the generated event schedule to the participants' communication devices. This makes it possible to create flexible schedules that reflect the interests of individual participants.

[0668] "Participants" refers to individuals or people who participate in activities or events within a given event.

[0669] "Activity data" refers to information about participants' past event participation history and behavioral patterns based on their interests.

[0670] An "information storage device" refers to a device that has the function of systematically storing data and allowing it to be referenced as needed.

[0671] A "generative algorithm" refers to a computational method used to analyze participant activity data and derive the optimal event schedule.

[0672] "Event schedule" refers to a schedule that shows the times and order of events and activities that participants can take part in.

[0673] "Communication device" refers to an electronic device used to send and receive information to and from participants.

[0674] The system in this invention is an advanced technology that generates an optimal event schedule based on participants' interests. To implement the invention, the system mainly consists of three entities: a "server," a "terminal," and a "user." Each entity plays a specific role, and the system functions effectively by coordinating with each other as a whole.

[0675] First, the server collects participants' past activity data and stores it in an information storage device. This information storage device is implemented in a format such as an SQL database, efficiently managing participants' past event participation history and interest data. The server also uses a generation algorithm to analyze participants' activity data and generate an optimal event schedule for each participant. A widely used machine learning model can be applied as the generation algorithm, enabling the generation of schedules that take into account the different interests and preferences of participants.

[0676] Next, the server transmits the generated event schedule to the participants' communication devices, i.e., terminals. The terminals provide an interface for visually presenting this schedule to the users. Specifically, the terminals receive the data and display it visually through the user interface in a way that is intuitively easy for participants to understand.

[0677] Users can use the terminal interface to review the presented event schedule and make adjustments according to their interests and convenience. For example, if they want to prioritize a particular activity, they can change the time of that activity on the terminal. The adjusted event schedule is then sent back to the server and recorded as the latest state in the server's information storage device. This ensures that participants have the optimal experience according to the time.

[0678] As a concrete example of such a system, if a participant is interested in art, the server considers that participant's past participation history in art-related events and prioritizes scheduling museum visits, painting workshops, and similar activities. This allows participants to attend events that best match their interests.

[0679] As an example of a prompt in a generative AI model, the instructions the system receives might be the following text:

[0680] "Based on participants' past activity data, generate an optimal event schedule. Prioritize activities that will pique their interest and propose a visually clear and easy-to-understand format for displaying the schedule on their devices."

[0681] This prompt allows the system to leverage its technical advantages to design an event experience that aligns with the individual needs of each participant.

[0682] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0683] Step 1:

[0684] The server collects data on participants' past activities.

[0685] The system acquires data such as event participation history and areas of interest as input, and stores this data in an information storage device on the server. Specifically, the server retrieves data from various sources, organizes it in an SQL database, and stores it. This creates a comprehensive profile of the participant's preferences and interests.

[0686] Step 2:

[0687] The server uses a generated AI model to analyze the collected activity data.

[0688] The server receives accumulated data as input and prompts the generating AI model to perform analysis. Specifically, the AI ​​model analyzes the participants' past behavioral patterns and generates an optimal event schedule for each participant. This process utilizes machine learning algorithms, and the output is a prioritized event schedule.

[0689] Step 3:

[0690] The server sends the generated event schedule to the terminal.

[0691] The event schedule generated by the AI ​​model is used as input, and the server converts it into JSON format and transmits it to the terminal. Specifically, data is transferred from the server to the terminal using the HTTP protocol, and the terminal receives it. This prepares the event information that is most suitable for the participant.

[0692] Step 4:

[0693] The terminal visually displays the received event schedule to the user.

[0694] The event schedule received from the server is used as input, and the terminal provides an interface to visually display it. Specifically, a graphical user interface is used to display the schedule and activity details on the screen. This makes it easier for the user to intuitively understand the event schedule.

[0695] Step 5:

[0696] The user reviews the presented schedule and makes adjustments as needed.

[0697] The input is an event schedule displayed on the device, and the user adjusts the schedule through drag-and-drop and other methods. Specifically, it is possible to select activities that are prioritized and change their time and order. This operation enables the customization of the schedule to suit the user's individual interests.

[0698] Step 6:

[0699] The terminal resends the adjusted schedule to the server.

[0700] The event schedule, modified by the user, is used as input, and the terminal sends it back to the server in JSON format. In the actual processing, the server records this data again in the information storage device, keeping it up-to-date. This ensures that participants' schedules are always managed based on the latest information.

[0701] (Application Example 1)

[0702] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0703] Existing content distribution services face the challenge of efficiently providing content tailored to user interests. In particular, they lack sufficient individualized support that leverages the characteristics of visual display devices, limiting the user experience. Therefore, there is a need for more personalized content presentation and scheduling based on user interests and behavioral patterns.

[0704] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0705] In this invention, the server includes means for collecting past behavioral data of participants and storing it in an information storage device; means for analyzing past behavioral data of participants using a generation model and generating an optimal timetable for each participant; means for transmitting and displaying the generated timetable on the participant's information terminal; means for presenting a content list to participants using a visual display device; means for synchronizing selected content from the content list with the information storage device and coordinating information with other devices; and means for collecting participants' feedback or evaluation information and reflecting it in the generation of the next timetable. This enables individually optimized display of content according to user interests, as well as real-time synchronization and adjustment of information.

[0706] A "participant" is a user of the service within the system and the entity that provides information about their individual actions.

[0707] "Behavioral data" refers to information that records the choices and activities that participants have made in the past, and it is the data that forms the basis of the analysis.

[0708] An "information storage device" is a storage medium within a system that stores accumulated behavioral data and generated timetables.

[0709] A "generative model" is a mathematical or algorithmic computational method used to analyze past behavioral data.

[0710] A "timetable" is a plan or schedule created to guide participants' activities based on the analysis results.

[0711] An "information terminal" is an electronic device used by participants to access the system's functions.

[0712] A "visual display device" is a display device used to provide information to participants visually, and includes glasses-type devices.

[0713] A "content list" is a list of information or media items selected based on the participants' interests.

[0714] "Information sharing" refers to the act of synchronizing or sharing data between multiple devices.

[0715] "Feedback or evaluation information" refers to the subjective evaluations that participants give to content or services, and this data is used to optimize future offerings.

[0716] The system realizing this invention utilizes various devices and software to deliver and schedule optimal content based on participants' interests. The main components are a server, an information terminal, and a visual display device.

[0717] The server collects and stores participants' past behavioral data using an information storage device. A cloud database such as Firebase is used for this purpose. Next, a generative AI model such as TensorFlow is used to analyze the collected behavioral data and generate a personalized schedule based on the participants' interests. The generated schedule is then sent to the participants' information terminals via the cloud service.

[0718] Participants' information terminals will use Flutter or similar tools to build a user interface and display the generated timetable. Visual display devices, such as glasses (Google Glass, for example), will present users with a list of content in real time, and users will select content of interest from that list. The selected content will be synchronized via Firebase, maintaining information sharing with other devices.

[0719] Furthermore, users input their impressions and evaluations of the provided content and send them from their devices to the server. This feedback information plays a crucial role in the optimization process for generating future schedules and content lists.

[0720] As a concrete example, consider the presentation of content at a music festival. Based on data from artists the user has watched in the past, they are recommended appropriate live performances from artists scheduled to participate in the next festival. In this case, an example of a prompt would be, "Based on the user's past viewing history, please suggest new live videos this week that might be of particular interest to them."

[0721] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0722] Step 1:

[0723] The server collects participants' past behavioral data from a cloud database. The input is behavioral data stored in cloud storage, and the output is a dataset for analysis. This dataset integrates information including participants' past choices and interests.

[0724] Step 2:

[0725] The server analyzes the collected dataset using a generative AI model. The input is the dataset from Step 1, and the output is a timetable optimized for each participant. The AI ​​model analyzes patterns in the data and identifies the content and activities that best match the participants' interests.

[0726] Step 3:

[0727] The server sends the generated timetable to the participants' information terminals via the cloud. The input here is the timetable generated in step 2, and the output is a visual display of the timetable on the terminal. The information terminal displays this timetable in its user interface, making it easy for participants to check.

[0728] Step 4:

[0729] The user reviews a list of content presented through a visual display device and selects content of interest. The input is the content list displayed on the terminal, and the output is information about the selected content. This selection information is transmitted from the visual display device to the terminal and synchronized for the next step.

[0730] Step 5:

[0731] The terminal synchronizes the content information selected by the user to a cloud database. The input is the content information selected in step 4, and the output is the synchronization status to the information storage device. The cloud database receives this and uses it as data to interact with other devices.

[0732] Step 6:

[0733] Users input their thoughts and evaluations of the content from their devices and send them to the server. The input consists of user evaluation comments and feedback data, while the output is a feedback record used in the next optimization process. The server stores this feedback information and incorporates it into the next timetable generation.

[0734] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0735] This invention provides a system that offers an event schedule based on participants' interests and combines it with an emotion engine that recognizes users' emotions. The system aims to provide participants with a more highly personalized event experience.

[0736] This system primarily consists of four components: a server, a terminal, a user, and an emotion engine. First, the server collects past behavioral data from participants and stores it in a database. This data includes events the participant has previously attended, topics they have shown interest in, and their ratings. Based on the collected data, the server uses a generative model to analyze the data and generate an optimized event schedule for each participant.

[0737] The generated schedule is sent from the server to each participant's device and displayed on their device. Users can review this schedule and make manual adjustments as needed. The adjusted schedule is sent to the server in real time and kept up-to-date on the server.

[0738] A distinctive component of this invention is an emotion engine. The emotion engine recognizes emotions in real time from the user's facial expressions, tone of voice, and other factors. This information is used by the server to optimize the schedule. For example, if a user shows positive emotions towards a particular activity, the server will set a higher priority for that activity. If a user shows negative emotions, the server can suggest alternative activities and automatically restructure the schedule.

[0739] For example, if the emotion engine detects many positive emotions from a user on the first day of an exhibition, the server will present a schedule for the second day that reflects an increase in activities similar to those of that user. Conversely, for sessions with negative ratings, similar activities can be removed to improve the overall experience. In this way, the system can incorporate real-time emotion information from users and provide an event experience optimized for participants.

[0740] The following describes the processing flow.

[0741] Step 1:

[0742] The server collects past behavioral data from event participants and stores it in a database. This includes detailed information such as the activities they participated in and the topics they showed interest in.

[0743] Step 2:

[0744] The server uses a generative model to analyze the collected behavioral data. This generates an optimized event schedule for each participant, creating a schedule tailored to individual interests.

[0745] Step 3:

[0746] The server sends the generated schedule to the participants' devices. The devices then visually display this schedule to the users and prompt them for confirmation.

[0747] Step 4:

[0748] Users check the schedule displayed on their device and make manual adjustments as needed. These adjustments include changing the priority of activities they want to participate in and rearranging the times.

[0749] Step 5:

[0750] The terminal sends the user's adjustments to the server in real time, and the latest information is managed on the server.

[0751] Step 6:

[0752] The emotion engine recognizes the user's facial expressions and voice tone in real time and generates emotion data. This emotion data is categorized into positive, negative, neutral, and other categories.

[0753] Step 7:

[0754] The server re-evaluates the schedule based on the emotion data received from the emotion engine. If the emotion is positive, it prioritizes the relevant activity; if the emotion is negative, it suggests an alternative activity.

[0755] Step 8:

[0756] The device notifies the user of the re-evaluated schedule and presents a new schedule that reflects the suggestions.

[0757] Step 9:

[0758] After the event ends, users enter feedback from their devices and send it to the server. This feedback data is used to generate future event schedules and is reflected in the analysis results.

[0759] (Example 2)

[0760] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0761] Current event scheduling systems have the challenge of making it difficult to provide an experience optimized for each individual participant. Specifically, they cannot reflect participants' individual interests and emotions in real time, and are limited to providing an experience based on a fixed schedule. As a result, it becomes difficult to improve participant satisfaction.

[0762] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0763] In this invention, the server includes means for collecting information on participants' past behavior and storing it in an information storage medium; means for analyzing the participants' past behavior information using a generative model and generating an optimal activity schedule for each participant; and means for analyzing the characteristics of participants' facial expressions and voices and acquiring emotional information. This makes it possible to provide an optimized activity schedule in real time according to the participants' interests and emotions.

[0764] "Participants" refers to individual users involved in an event or activity.

[0765] "Past behavioral information" refers to data about events participants have previously attended, their interests, and their evaluations.

[0766] An "information storage medium" refers to a storage device used to accumulate and manage data.

[0767] A "generative model" refers to an algorithm or method used to analyze data and generate specific deliverables.

[0768] "Activity schedule" refers to a schedule outlining the events and activities that participants will be taking part in in the future.

[0769] "Information terminal" refers to an electronic device used by participants to receive, view, or manipulate information.

[0770] "Facial and vocal characteristics" refers to visual or auditory information obtained from the participants' facial expressions and speech.

[0771] "Emotional information" refers to data that indicates the emotional state of participants.

[0772] Prioritization refers to the act of assigning relative importance to a series of items or tasks.

[0773] "Evaluation information" refers to data that shows the opinions and impressions that participants have about their experiences and activities.

[0774] To implement this invention, a system consisting mainly of a server, terminal, user, and emotion engine is constructed.

[0775] The server acts as the central hub, collecting and processing information about the past behavior of participating users. This includes events the user has previously attended, topics they have shown interest in, and their ratings. A common database management system can be used to store this data. Furthermore, the server uses a generative AI model to analyze this data and create an activity schedule optimized for the user. This process can utilize programming languages ​​such as Python or machine learning libraries such as TensorFlow.

[0776] The terminal functions as a device for users to check their activity schedule and edit it as needed. Schedules sent from the server are displayed on the terminal. Users can adjust their schedules on this terminal, and these adjustments are immediately sent to the server. The HTTP protocol could be used for this.

[0777] Furthermore, this invention includes an emotion engine. The emotion engine acquires emotional information from the user's facial expressions and voice. This information is collected using a camera and microphone and analyzed using OpenCV or other speech recognition technologies. Based on this emotional information, the server can further personalize the user's schedule.

[0778] For example, if a user expresses positive emotions through the emotion engine on the first day of an exhibition, the server will generate a schedule for the second day that includes similar activities. Conversely, for sessions that receive negative ratings, similar content can be removed, and the schedule can be reorganized to provide a better experience.

[0779] An example of a prompt message is, "Generate an optimal schedule based on the user's preferred activities and readjust it to reflect sentiment data." This allows the system to provide participants with a more personalized and optimized activity experience.

[0780] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0781] Step 1:

[0782] The server collects information about the user's past behavior and stores it in a data storage medium. Specifically, it obtains data such as events the user has previously participated in, topics they are interested in, and ratings through APIs and log files. This input data is stored in a structured format using a database management system.

[0783] Step 2:

[0784] The server performs data analysis using a generative AI model based on collected past behavioral information. This analysis extracts user interests and tendencies and generates an optimal activity plan. Here, behavioral information stored in the database is taken as input, and a predicted activity plan is obtained as output. Statistical calculations are performed using a machine learning framework.

[0785] Step 3:

[0786] The server sends the generated activity schedule to the user's terminal. This process uses the HTTP protocol to send the schedule information to the terminal in JSON format. The terminal receives this data as input and displays the schedule in the user interface.

[0787] Step 4:

[0788] Users review their activity schedule displayed on their device and make adjustments as needed. Specifically, they can change, add, or delete appointments using drag-and-drop functionality or selection buttons. This adjusted schedule is then resent from the device to the server, where it is updated to the latest state.

[0789] Step 5:

[0790] The emotion engine analyzes the user's facial expressions and voice tone in real time to acquire emotional information. It takes data from a camera and microphone as input and converts it into emotional information using OpenCV and speech recognition technology. This information generates output indicating the user's current emotional state.

[0791] Step 6:

[0792] The server uses the acquired sentiment information to automatically readjust the activity schedule. It receives sentiment information as input, prioritizes activities that elicit positive emotions from the user, and suggests alternatives for activities that receive negative ratings. This readjusted schedule is then generated and sent back to the device.

[0793] (Application Example 2)

[0794] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0795] Modern commercial facilities and event venues are required to provide visitors with personalized experiences. Traditional methods struggle to deliver the optimal experience tailored to participants' interests and lack the ability to dynamically adjust in real time to reflect emotions and interests. In particular, there is a need to quickly reflect collected emotional information and individually optimize the visitor experience.

[0796] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0797] In this invention, the server includes means for collecting and storing past behavioral data of participants in a database, means for analyzing past behavioral data of participants using a generative model and generating an optimal event plan for each participant, and means for acquiring participants' emotional information in real time and dynamically optimizing the event plan using that information. This makes it possible to provide a personalized experience based on participants' past behavior and real-time emotions, thereby improving visitor satisfaction.

[0798] "Participants" are individuals who visit a specific event or commercial facility.

[0799] "Behavioral data" refers to a collection of information about the actions and choices that participants have made in the past.

[0800] A "database" is a system that stores data and enables efficient management and retrieval.

[0801] A "generative model" is an algorithm that analyzes participants' behavioral data and generates results tailored to a specific purpose.

[0802] An "event plan" is a proposed schedule that optimizes the events and activities that participants will experience.

[0803] "Information processing equipment" refers to electronic devices such as mobile terminals and computers used by participants.

[0804] "Emotional information" refers to data about the emotional state obtained from participants' facial expressions and voice.

[0805] "Dynamic optimization" is a process of immediately adjusting plans and proposals based on real-time information.

[0806] "Evaluation information" refers to data that includes opinions and impressions of participants' experiences.

[0807] The system that realizes this invention consists of a server, terminals, users, and an emotion engine that complements them. The server accesses a database to collect and store past behavioral data of participants and analyzes it using a generative model to generate an optimized event plan for each participant. This makes it possible to personalize events based on participants' past interests and behaviors.

[0808] The generated event plan is transmitted via the internet to participants' information processing devices (e.g., smartphones, tablets). The devices display the received information, allowing participants to review and adjust the plan based on this information. This adjustment information is then sent back to the server and updated in real time.

[0809] The emotion engine collects user facial expressions via camera and audio via microphone, extracting emotional information in real time. Specifically, it performs image analysis using OpenCV and DeepFace, converts audio to text using the Google Cloud Speech-to-Text API, and then evaluates emotions using natural language processing techniques. This allows the system to dynamically adjust plans according to the user's emotions, providing a better experience.

[0810] For example, when a user is searching for products in a store, if their facial expression is positively recognized by their smartphone camera, the server can prioritize suggesting products from a specific brand. Conversely, if there is a negative reaction, the server will refrain from suggesting related products.

[0811] An example of a prompt to input into the generating AI model is: "Identify in real time what products the user is interested in in a physical store, and consider how to present the most suitable offers and information for that day." This prompt is used to generate a scenario that personalizes product suggestions for the user.

[0812] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0813] Step 1:

[0814] The server collects past behavioral data from participants from a database. Inputs include past behavioral records, topics of interest, and evaluation data. Based on this data, the server organizes and integrates the participants' past history and prepares it for analysis.

[0815] Step 2:

[0816] The server uses the collected behavioral data to launch a generative model and perform analysis. The input is behavioral data, and the generative AI model is used to analyze behavioral patterns and their correlations. As output, an event plan optimized for each participant is generated.

[0817] Step 3:

[0818] The server sends the generated event plan to the participants' terminals via the internet. The terminals receive this event plan internally and display it visually on their screens. The input here is the event plan data, and the output is what is displayed on the terminals.

[0819] Step 4:

[0820] Users view the event schedule displayed on their terminal and make adjustments as needed. Users input requests such as desired destinations and time slots. The terminal receives this information and resends it to the server, updating the schedule.

[0821] Step 5:

[0822] The emotion engine captures the user's facial expressions with a camera and records their voice with a microphone. The input consists of the user's real-time facial expressions and voice. OpenCV and the Google Cloud Speech-to-Text API are used to extract this data as emotional information. The output is a positive or negative emotional evaluation.

[0823] Step 6:

[0824] The server dynamically optimizes event plans using emotion information received in real time. Inputs are emotion information and existing event plans, and the system uses a generative AI model to adjust the plans. The output is an updated event plan based on the emotions.

[0825] Step 7:

[0826] The terminal receives the updated event plan again from the server and presents it to the user. The final output is a display of the optimized event plan, with an example prompt message being, "Identify in real time what products the user is interested in in-store and consider how to present the most suitable offers and information for that day."

[0827] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0828] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0829] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0830] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0831] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0832] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0833] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0834] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0835] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0836] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0837] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0838] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0839] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0840] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0841] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0842] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0843] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0844] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0845] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0846] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0847] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0848] The following is further disclosed regarding the embodiments described above.

[0849] (Claim 1)

[0850] A means of collecting past behavioral data of participants and storing it in a database,

[0851] A method for analyzing participants' past behavioral data using a generative model and generating an optimal event schedule for each participant,

[0852] A means of sending and displaying the generated event schedule on the participants' devices,

[0853] A means of accepting schedule adjustments from participants and managing updated schedules,

[0854] A means for participants to share the generated schedule with other participants,

[0855] A system that includes this.

[0856] (Claim 2)

[0857] The system according to claim 1, wherein the generated event schedule is prioritized based on the interests of the participants.

[0858] (Claim 3)

[0859] The system according to claim 1, which collects participant feedback data and reflects that data in generating the next event schedule.

[0860] "Example 1"

[0861] (Claim 1)

[0862] A means of aggregating participants' past activity data and storing it in an information storage device,

[0863] A means for analyzing participants' past activity data using a generation algorithm and generating an optimal event schedule for each participant,

[0864] A means for transmitting and displaying the generated event schedule to the participants' communication devices,

[0865] A means of accepting schedule adjustments from participants and managing updated schedules,

[0866] A means for participants to share the generated schedule with other participants,

[0867] A system that includes this.

[0868] (Claim 2)

[0869] The system according to claim 1, wherein the generated event schedule is ordered based on the interests of the participants.

[0870] (Claim 3)

[0871] The system according to claim 1, which collects participant opinion data and reflects that data in generating the schedule for the next event.

[0872] "Application Example 1"

[0873] (Claim 1)

[0874] A means for collecting past behavioral data of participants and storing it in an information storage device,

[0875] A method for analyzing participants' past behavioral data using a generative model and generating an optimal schedule for each participant,

[0876] A means of transmitting and displaying the generated timetable on the participant's information terminal,

[0877] A means of accepting timetable adjustments from participants and managing the updated timetable,

[0878] A means for participants to share the generated schedule with other participants,

[0879] A means of presenting a content list to participants using a visual display device,

[0880] A means for synchronizing the content selected from the content list with an information storage device and for information exchange with other devices,

[0881] A means of collecting participants' feedback or evaluation information and reflecting it in the generation of the next schedule,

[0882] A system that includes this.

[0883] (Claim 2)

[0884] The system according to claim 1, wherein the generated schedule is prioritized based on the participants' interests and displayed directly on the participants' visual display devices.

[0885] (Claim 3)

[0886] The system according to claim 1, which optimizes the selection of content for the next session by utilizing interactive feedback and timetable adjustments after participation.

[0887] "Example 2 of combining an emotion engine"

[0888] (Claim 1)

[0889] A means of collecting information on participants' past behavior and storing it in an information storage medium,

[0890] A method for analyzing participants' past behavioral information using a generative model and generating an optimal activity plan for each participant,

[0891] A means of sending and displaying the generated activity schedule on the participant's information terminal,

[0892] A means of accepting schedule adjustments from participants and managing updated schedules,

[0893] A method for analyzing participants' facial expressions and vocal characteristics to obtain emotional information,

[0894] A means of automatically readjusting activity schedules using acquired emotional information,

[0895] A means for participants to share the generated schedule with other participants,

[0896] A system that includes this.

[0897] (Claim 2)

[0898] The system according to claim 1, wherein the generated activity schedule is prioritized based on the participants' interests and feelings.

[0899] (Claim 3)

[0900] The system according to claim 1, which collects participant evaluation information and reflects that information in generating the next activity schedule.

[0901] "Application example 2 when combining with an emotional engine"

[0902] (Claim 1)

[0903] A means of collecting past behavioral data of participants and storing it in a database,

[0904] A method for analyzing participants' past behavioral data using a generative model and generating an optimal event plan for each participant,

[0905] A means for transmitting and displaying the generated event plan on the participant's information processing device,

[0906] A means of accepting adjustments to the plan by participants and managing the updated plan,

[0907] A means of acquiring participants' emotional information in real time and using that information to dynamically optimize event planning,

[0908] A means for participants to share the generated plan with other participants,

[0909] A system that includes this.

[0910] (Claim 2)

[0911] The system according to claim 1, wherein the generated event schedule is prioritized based on the interests and feelings of the participants.

[0912] (Claim 3)

[0913] The system according to claim 1, which collects participant evaluation information and reflects that information in generating the next event plan. [Explanation of Symbols]

[0914] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting past behavioral data of participants and storing it in a database, A method for generating an optimal event schedule for each participant by analyzing past behavioral data of participants using a generative model, A means of sending and displaying the generated event schedule on the participants' devices, A means of accepting schedule adjustments from participants and managing updated schedules, A means for participants to share the generated schedule with other participants, A system that includes this.

2. The system according to claim 1, wherein the generated event schedule is prioritized based on the interests of the participants.

3. The system according to claim 1, which collects participant feedback data and reflects that data in generating the next event schedule.

Images